README.md

---
tags:
- merge
- mergekit
- davidkim205/Rhea-72b-v0.5
- abacusai/Smaug-72B-v0.1
base_model:
- davidkim205/Rhea-72b-v0.5
- abacusai/Smaug-72B-v0.1
license: apache-2.0
---

![](https://raw.githubusercontent.com/saucam/models/main/pyrhea.png)

# Pyrhea-72B

Pyrhea-72B is a merge of the following models using [Mergekit](https://github.com/arcee-ai/mergekit):
* [davidkim205/Rhea-72b-v0.5](https://huggingface.co/davidkim205/Rhea-72b-v0.5)
* [abacusai/Smaug-72B-v0.1](https://huggingface.co/abacusai/Smaug-72B-v0.1)

## 🧩 Configuration

```yamlname: Pyrhea-72B
models:
  - model: davidkim205/Rhea-72b-v0.5
    parameters:
      density: 0.5
      weight: 0.6
    # No parameters necessary for base model
  - model: abacusai/Smaug-72B-v0.1
    parameters:
      density: 0.5
      weight: 0.4
merge_method: dare_ties
base_model: davidkim205/Rhea-72b-v0.5
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "saucam/Pyrhea-72B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```